Firefly Algorithm --- Implementation of Firefly algorithm in Python

📋 About • 📦 Installation • 🚀 Usage • 📚 Reference Papers • 📄 Cite us • 🔑 License

📋 About

This package implements a nature-inspired algorithm for optimization called Firefly Algorithm (FA) in Python programming language. 🌿🔍💻

📦 Installation

To install FireflyAlgorithm with pip, use:

pip install fireflyalgorithm

To install FireflyAlgorithm on Fedora, use:

dnf install python-fireflyalgorithm

To install FireflyAlgorithm on Arch Linux, please use an AUR helper:

$ yay -Syyu python-fireflyalgorithm

To install FireflyAlgorithm on Alpine Linux, use:

$ apk add py3-fireflyalgorithm

🚀 Usage

from fireflyalgorithm import FireflyAlgorithm
from fireflyalgorithm.problems import sphere

FA = FireflyAlgorithm()
best = FA.run(function=sphere, dim=10, lb=-5, ub=5, max_evals=10000)

print(best)

Test functions 📈

In the fireflyalgorithm.problems module, you can find the implementations of 33 popular optimization test problems. Additionally, the module provides a utility function, get_problem, that allows you to retrieve a specific optimization problem function by providing its name as a string:

from fireflyalgorithm.problems import get_problem

# same as from fireflyalgorithm.problems import rosenbrock
rosenbrock = get_problem('rosenbrock')

For more information about the implemented test functions, click here.

Command line interface 🖥️

The package also comes with a simple command line interface which allows you to evaluate the algorithm on several popular test functions. 🔬

firefly-algorithm -h

usage: firefly-algorithm [-h] --problem PROBLEM -d DIMENSION -l LOWER -u UPPER -nfes MAX_EVALS [-r RUNS] [--pop-size POP_SIZE] [--alpha ALPHA] [--beta-min BETA_MIN] [--gamma GAMMA] [--seed SEED]

Evaluate the Firefly Algorithm on one or more test functions

options:
  -h, --help            show this help message and exit
  --problem PROBLEM     Test problem to evaluate
  -d DIMENSION, --dimension DIMENSION
                        Dimension of the problem
  -l LOWER, --lower LOWER
                        Lower bounds of the problem
  -u UPPER, --upper UPPER
                        Upper bounds of the problem
  -nfes MAX_EVALS, --max-evals MAX_EVALS
                        Max number of fitness function evaluations
  -r RUNS, --runs RUNS  Number of runs of the algorithm
  --pop-size POP_SIZE   Population size
  --alpha ALPHA         Randomness strength
  --beta-min BETA_MIN   Attractiveness constant
  --gamma GAMMA         Absorption coefficient
  --seed SEED           Seed for the random number generator

Note: The CLI script can also run as a python module (python -m fireflyalgorithm ...).

📚 Reference Papers

I. Fister Jr., X.-S. Yang, I. Fister, J. Brest, D. Fister. A Brief Review of Nature-Inspired Algorithms for Optimization. Elektrotehniški vestnik, 80(3), 116-122, 2013.

I. Fister Jr., X.-S. Yang, I. Fister, J. Brest. Memetic firefly algorithm for combinatorial optimization in Bioinspired Optimization Methods and their Applications (BIOMA 2012), B. Filipic and J.Silc, Eds. Jozef Stefan Institute, Ljubljana, Slovenia, 2012

I. Fister, I. Fister Jr., X.-S. Yang, J. Brest. A comprehensive review of firefly algorithms. Swarm and Evolutionary Computation 13 (2013): 34-46.

📄 Cite us

Fister Jr., I., Pečnik, L., & Stupan, Ž. (2023). firefly-cpp/FireflyAlgorithm: 0.4.3 (0.4.3). Zenodo. https://doi.org/10.5281/zenodo.10430919

🔑 License

This package is distributed under the MIT License. This license can be found online at http://www.opensource.org/licenses/MIT.

Disclaimer

This framework is provided as-is, and there are no guarantees that it fits your purposes or that it is bug-free. Use it at your own risk!